The global drive towards net-zero has accelerated the adoption of carbon fibre reinforced polymers (CFRP) for lightweight structures in various sectors such as aerospace, automotive, energy and biomedical. Mechanical machining of CFRP is often necessary to meet dimensional or assembly-related requirements. However, significant challenges including surface defects (delamination, burr, surface roughness), rapid tool wear and material transition issues in drilling CFRP/metal stack, underscore the need for effective, automated process prediction / optimization for improved machining performance. Conventional physics-based models often fall short due to their reliance on extensive computational resources and inability to capture CFRP’s complex machining dynamics arising from thermo-mechanical load coupling and process uncertainties. To address these limitations, recent advancements in artificial intelligence (AI) offer promising, data-driven solutions that reduce reliance on domain-specific knowledge while delivering fast, accurate predictions by uncovering patterns within dataset. This provides a promising solution towards intelligent CFRP machining process with improved quality and efficiency. To date, there is a lack of comprehensive, up-to-date review of data-driven methods in CFRP machining process prediction/optimization. This review fills this gap and provides a critical analysis of data-driven methods in four key application settings: (i) machining process characteristics and surface quality/defects prediction; (ii) tool wear prediction; (iii) material transition recognition in CFRP/metal stacks machining; (iv) vision-based surface defects recognition. By presenting a state-of-the-art overview of advances, challenges and future research directions, this review highlights the transformative potential of data-driven methods in advancing intelligent CFRP machining within the manufacturing value chain.

For traditional surrogate model-based methods, the distribution parameters of random variables will change with the enrichment of the data, ultimately leading to the reconstruction of surrogate model and reassessment of reliability, which often results in a wastage of computational resources. In response, an extended Kriging model-based method is proposed in this paper for efficient reliability analysis under parameters change. Different from the standard Kriging model, in addition to random variables, variable distribution parameters are also included in the proposed method to constitute the extended input variables. In this way, the updated Kriging model with prior parameter information can be directly treated as the initial surrogate model for the posterior problem. Consequently, there is no need to reconstruct the surrogate model if the distribution parameters change, and only one Kriging model is required for this method. The efficiency, robustness and accuracy of the proposed method are demonstrated through three examples. This study contributes to dynamic assessment techniques for structural reliability analysis.